Modelling And Applications In Mathematics Education Pdf

Article Menu

/ajax/scifeed/subscribe

Open Access Article

Modeling and Forecasting Cases of RSV Using Artificial Neural Networks

Departamento de Matemáticas y Estadística, Universidad de Córdoba, 230002 Montería, Colombia

Department of Mathematics, New Mexico Tech, Socorro, NM 87801, USA

Author to whom correspondence should be addressed.

^†

These authors contributed equally to this work.

Academic Editor: Konstantin Kozlov

Received: 25 October 2021 / Revised: 15 November 2021 / Accepted: 16 November 2021 / Published: 19 November 2021

Abstract

In this paper, we study and present a mathematical modeling approach based on artificial neural networks to forecast the number of cases of respiratory syncytial virus (RSV). The number of RSV-positive cases in most of the countries around the world present a seasonal-type behavior. We constructed and developed several multilayer perceptron (MLP) models that intend to appropriately forecast the number of cases of RSV, based on previous history. We compared our mathematical modeling approach with a classical statistical technique for the time-series, and we concluded that our results are more accurate. The dataset collected during 2005 to 2010 consisting of 312 weeks belongs to Bogotá D.C., Colombia. The adjusted MLP network that we constructed has a fairly high forecast accuracy. Finally, based on these computations, we recommend training the selected MLP model using 70% of the historical data of RSV-positive cases for training and 20% for validation in order to obtain more accurate results. These results are useful and provide scientific information for health authorities of Colombia to design suitable public health policies related to RSV. View Full-Text

► ▼ Show Figures

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited

SciFeed

Share and Cite

MDPI and ACS Style

Cogollo, M.R.; González-Parra, G.; Arenas, A.J. Modeling and Forecasting Cases of RSV Using Artificial Neural Networks. Mathematics 2021, 9, 2958. https://doi.org/10.3390/math9222958

AMA Style

Cogollo MR, González-Parra G, Arenas AJ. Modeling and Forecasting Cases of RSV Using Artificial Neural Networks. Mathematics. 2021; 9(22):2958. https://doi.org/10.3390/math9222958

Chicago/Turabian Style

Cogollo, Myladis R., Gilberto González-Parra, and Abraham J. Arenas 2021. "Modeling and Forecasting Cases of RSV Using Artificial Neural Networks" Mathematics 9, no. 22: 2958. https://doi.org/10.3390/math9222958

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Metrics

Article Access Statistics

For more information on the journal statistics, click here.

Multiple requests from the same IP address are counted as one view.

Article Access Map by Country/Region

Author Biographies

I obtained my doctorate in Applied Mathematics from the Polytechnic University of Valencia, Institute of Multidisciplinary Mathematics, Valencia, Spain. Thesis Title: Mathematical modelling of virus RSV: Qualitative properties, numerical solutions and validation for the case of the region of Valencia, Doctoral Thesis Cum Laude, May 2009. Adviser: Ph.D Lucas Antonio Jódar Sánchez. Master's degree in Mathematics, National of Colombia University, Medellín, Colombia. Thesis Title: Numerical solution of inverse problem by Discrete Mollification, July 1998. Adviser: Ph.D Carlos Enrique Mejía Salazar. Bachelor's degree in Mathematics and Physics, University of Cordoba, Montería, Córdoba, Colombia. July 1987. My main scientific research can be divided into the following three broad categories: Differential equations: I am interested in the formulation, analysis and implementation of new techniques for the study of the behavior of solutions of new models. Numerical Analysis: Numerical Solution of Ordinary and Partial Differential Equations, using Standard and Nonstandard Finite Difference Methods, which come from the modeling of problems of mathematical physics, engineering or science. Mathematical Biology: I am also interested in mathematical modeling and the theoretical analysis of biological phenomena, and the development of epidemiological models for the identification of threshold parameters.